AI Engineer · Barcelona
Hire an AI engineer in Barcelona who solves problems with software
Industrial engineer turned AI engineer and full stack developer. I solve problems with software, AI included: agents with MCP, apps, websites 10x faster, and paid acquisition with proper tracking. Barcelona-based, remote-friendly, founder-mode when you need it.
Deciding whether you need an engineer, a product, or a full-time hire? The buying guide is Hire an AI engineer: how to pick one who ships. This page is the offer.
Offer
What I take on.
01
AI agents & MCP
Production agents that call real tools: WhatsApp, CRMs, calendars, and internal APIs, via Model Context Protocol and LLM tool use. Multi-tenant where it matters, BYOK when cost control matters more.
02
AI-powered apps end-to-end
From brief to shipped SaaS: Next.js, TypeScript, Supabase, auth, billing hooks, and model pipelines that survive contact with real users.
03
Paid acquisition + tracking
Google and Meta campaigns with measurement that still works post-iOS14: GA4, GTM, server-side tracking, and dashboards so spend maps to outcomes instead of vibes.
What I build
Typical projects.
WhatsApp agents that answer and qualify leads
Claude replies in seconds, collects the lead's details with tool use, books appointments inside WhatsApp, and escalates to a human when needed. Multi-tenant, BYOK, Meta Cloud API direct. What booking costs, and whether to build or buy, is in WhatsApp appointment booking with AI: build or buy.
Claient case study →AI inside an existing product
A model woven into a real workflow instead of bolted on: a Claude Script Doctor and a dramatic-arc Hype Graph inside an act-based film production pipeline.
Dairector case study →AI SaaS shipped end-to-end
SEO drafts from real product data, on-brand imagery and editorial calendars, pushed straight into WordPress and Shopify from a single workspace.
Adorea.ai case study →On-device AI with no server
Subject masks, object removal, background removal and upscaling running in the browser with ONNX Runtime Web. Photos never leave the user's device.
Lightframes case study →Agents and tools wired to your systems
Agents that call CRMs, calendars and internal APIs through MCP or plain function calling, plus the automations and tracking that keep a team's workflow moving. What an agent should keep between sessions is in AI agent memory: what to store, what to forget.
MCP vs function calling →
Built for production
What keeps an agent working after the demo.
A demo makes one model call on the happy path. A production agent survives retries, timeouts, long conversations and leaked keys. These are the patterns I ship by default, each written up from real projects.
Idempotent webhooks
Incoming messages are claimed before processing, so a Meta retry never sends your lead the same reply twice.
Read the write-up →Durable long-running steps
A step log, a queue and tools that know whether they can run twice, so an agent that dies mid-task resumes instead of restarting.
Read the write-up →Bounded model cost
A rolling context window plus summary, prompt caching on the fixed prefix and real token and USD cost logged per account.
Read the write-up →Isolated data and keys
Row Level Security per tenant, API keys encrypted and server-only, and hard spend caps so a leaked key has a ceiling.
Read the write-up →
Proof
Shipped, not hypothetical.
LiveClaient: AI WhatsApp client agent with Claude
AI WhatsApp client agent: answers, qualifies, and books appointments 24/7. Live at 49 €/month + VAT.
Read case study →
LiveAdorea.ai: shipping an AI marketing product end-to-end
Shipping an AI marketing SaaS end-to-end: SEO, imagery, calendars, WP & Shopify.
Read case study →
ShippedDTC paid acquisition with tracking that recovers ROAS
DTC paid acquisition on Google + Meta: server-side tracking, creative tests, scaled ROAS.
Read case study →
LiveDairector: AI film production with Claude Script Doctor
AI film production platform: Claude Script Doctor, dramatic-arc analysis, script to post.
Read case study →
“Many inquiries reached us on WhatsApp outside business hours: which cava to gift, prices, shipping, and they went unanswered until the next day. Now Claient replies right away and that sale no longer slips away: we have noticed an increase in bottle orders since we turned it on.”
On-device AI in the browser: Lightframes, my open-source photo editor, runs its AI models in the user’s browser with ONNX Runtime Web: subject masks, MI-GAN object removal, IS-Net background removal and Real-ESRGAN upscaling. No uploads, no server, works offline as a PWA.
Writing
Writing on building with AI.
Engineering | November 18, 2026
Hire an AI engineer: how to pick one who ships
A buyer's guide to hiring an AI engineer for a project, not a job opening: when you need one, what to ask, the red flags, and how to scope the first engagement.
Engineering | October 14, 2026
AI agent development cost: what actually moves the number (2026)
What AI agent development really costs in 2026: build drivers, Anthropic model run rates, and when hiring an engineer is worth it. Grounded in Claient.
Engineering | October 21, 2026
MCP vs function calling: Claude and OpenAI differences (2026)
Function calling is how the model asks for a tool. MCP is how that tool is shared between apps. Claude and OpenAI wire both differently, and a SaaS integration usually needs a bit of each.
Engineering | October 7, 2026
Claude vs GPT for AI agents: what I actually ship with (2026)
Claude vs GPT for building AI agents, as of October 2026: the price tiers now mirror each other almost to the cent, so the choice comes down to API shape, caching and hosted tools. My verdict, a comparison table, and the production code behind it.
AI & Dev Trends | October 23, 2026
Claude Code vs Codex: pick by task, then set up both
Over 60% of T3 Code users who ran Codex also ran Claude Code. The useful question isn't which one wins, it's which job goes to which agent, what each costs, and how to make one repo work for both.
AI & Dev Trends | October 21, 2026
Durable AI agents: what happens when your agent dies mid‑task
Vercel just open-sourced durable-harness to keep Claude Code, Codex and other harnesses alive through crashes and timeouts. The pattern underneath matters more than the package: a step log, a queue, and tools that know whether they can run twice.
AI & Dev Trends | October 16, 2026
Claude Code cost per month: how to budget it before finance does
Accenture just capped Claude at $29 a month per employee, after some people were spending $1,000. What Claude Code actually costs in October 2026, and how to budget, measure and cap it without a panic memo.
AI & Dev Trends | October 28, 2026
Single agent vs multi‑agent: when subagents are worth it
Anthropic's October 2026 guidance: fold many subagents into one loop with skills and MCP tools, migrate one at a time, and keep a subagent only when it earns its own context. A practical single agent vs multi-agent checklist.
AI & Dev Trends | October 30, 2026
How to review AI‑generated code: a risk‑tier checklist
AI agents write more code, but review time is where it piles up. A practical risk-tier checklist for small teams: what can auto-merge, what needs a human, and how to stop agent-reviewer loops.
Engineering | August 12, 2026
Keeping Claude's token bill from ruining your month
Every reply resends the whole conversation, so a chatty user is quietly billing you for the same context over and over. Five levers that actually moved the number, in the order I found them.
How I work
Stack & process.
Default stack
- TypeScript
- Next.js
- React
- Node.js
- Python
- Supabase
- Claude / Anthropic
- OpenAI
- MCP
- WhatsApp Cloud API
- GA4 / GTM
- Google Ads
- Meta Ads
Flexible when the client stack requires it (PHP, WordPress, existing backends). The constant is shipping something users can touch.
Week 0–1
Scope & stack
Clarify the outcome, constraints, and success metrics. Pick the smallest stack that can ship, usually TypeScript / Next.js plus the model and tools you already trust.
Week 1–3
Build the spine
Core flows first: auth, data model, the agent or LLM path, and one happy-path integration. You get something clickable early, not a wall of slides.
Week 3–5
Harden & instrument
Edge cases, observability, cost controls, and tracking. If growth is in scope, wire campaigns and attribution before scaling spend.
Ongoing
Ship & iterate
Launch, watch real usage, then tighten prompts, tools, and funnels. I stay close through the first production weeks so nothing drifts.
FAQ
Hiring an AI engineer: quick answers.
- What does an AI engineer do for a business?
- Turns a business problem into working software where a model does part of the job: an agent that answers customers, a tool that drafts or classifies work, a feature inside your product. Most of the work is not the prompt but everything around it: integrations with your systems, permissions, cost control, failure handling and tracking, so it keeps working after launch.
- Who is a good fit to hire you as an AI engineer?
- Founders and teams that need an AI-powered app or agent shipped end-to-end, not just a prototype. Ideal when product, engineering, and (optionally) paid acquisition need to move together.
- Do you build MCP and production AI agents?
- Yes. Agents with tool use, WhatsApp and API integrations, multi-tenant setups, and Model Context Protocol where it fits. Claient, my WhatsApp agent that answers and qualifies leads with Claude, is one in production. The bar is production use, not a weekend demo.
- How does a project start, and how long does it take?
- With a clear outcome and a short discovery week to fix scope, constraints and success criteria. Then the build runs in 3–5 week slices with something usable early, and I stay close through the first production weeks. Timelines depend on scope and on the integrations involved, so I give one after the discovery week, not before.
- What stack do you use?
- TypeScript, Next.js, React and Node.js by default, Python when it fits, Supabase for data and auth, Claude or OpenAI for models, MCP and the WhatsApp Cloud API for integrations, and GA4, GTM, Google Ads and Meta Ads for tracking and growth. I adapt to your stack when it requires it (PHP, WordPress, existing backends).
- Are you available remotely from Barcelona?
- Yes. Based in Barcelona and hybrid/remote-friendly. I work in English, Spanish and Catalan, and collaboration works over email, LinkedIn, and the usual async tools.
- How do you handle data privacy and API keys?
- Data stays separated per customer with Row Level Security, API keys live encrypted and are only ever called from the server, and spend caps limit the damage if a key leaks. When the data shouldn't leave the device at all, models can run in the browser, as they do in Lightframes, with no uploads.
- How do I contact you to start?
- Email me at joan.comadran2@gmail.com or message me on LinkedIn with what you want live in the next few weeks and the problem behind it. I reply with questions, then a proposed scope.
Get in touch
Let’s ship the agent, or the product.
Tell me what you want live in the next few weeks. AI engineering, full-stack AI apps, paid acquisition rebuilds. If it’s interesting to build, I’m in.